Xuelin Wang

Bio: Xuelin Wang is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Stereo camera & Computer stereo vision. The author has an hindex of 3, co-authored 5 publications receiving 34 citations.

A combined 2D-3D vision system for automatic robot picking

Abstract: This paper presents a new vision technique for an industrial robot to pick up randomly placed workpieces. The proposed approach combines 2D and 3D vision for efficiently determining the spatial position of a target object in cluttered scenes. 2D vision permits to quickly detect and locate objects of interest, thus reducing significantly the processing time. The location of an extracted 2D region (a detected object) is then passed to the 3D vision module to determine its world coordinate. Finally the 3D position information is sent to the robot manipulator for automatic picking. The test results show the effectiveness of the proposed system.

A shape-based stereo matching algorithm for binocular vision

Abstract: Binocular stereo vision is an important branch of the research area in computer vision. Stereo matching is the most important process in binocular vision. In this paper, a new stereo matching scheme using shape-based matching (SBM) is presented to improve the depth reconstruction method of binocular stereo vision systems. The method works in two steps. First, an operator registers the pattern including the key features of an object to be measured. Then during the operation stage, the stereo camera snaps stereo images and finds the patterns in right and left images separately by means of the SBM. The 3D positions of the object are calculated by using the corresponding points of the stereo images and the projection matrices of the stereo camera. Since we apply robust image processing algorithms, such as the SBM, the proposed method becomes more reliable than the conventional stereo vision systems.

An automatic robot unstacking system based on binocular stereo vision

Abstract: Unstacking is a process widely used in many industrial applications. This paper proposes an automatic unstacking system using an industrial robot and stereo vision. To detect a package to be picked, a shape-based matching (SBM) method is applied on 2D images. The 3D position of a selected package among pick-up candidates is calculated by acquiring a pair of correspondence points in the left and right images of a binocular camera. In order to improve the 3D pose estimation performance, the SBM method is also used instead of the conventional stereo matching method. Since SBM is a robust image processing algorithm, the proposed vision system can be employed for various general-purpose applications. Furthermore an unstacking strategy, in which the robot automatically picks packages in each layer of the stack, is established. Experimental results on a stack of commercial packages validated the 3D positioning accuracy of the vision system and the robot successfully manipulates the stacked packages.

An approach based on particle swarm optimization for fast object detection

Abstract: This paper describes a new object detection approach using particle swarm optimization (PSO). The approach is based on the idea that the task of finding a well-matched subwindow (object) can be formulated as an integer nonlinear optimization problem (INOP). We use PSO to solve this formulated INOP. Experiments in the domain of face detection are presented and the results show the effectiveness of the proposed method.

Master-slave force control based on grey GM(1,1) model of robot gripper

Abstract: This paper describes the position and force control of a novel two-finger gripper using force control technology, a master-slave force control strategy is deveoped for making the force track the desired force quickly with lower overshoot. PID controller is adapted to the position system for the master finger, and force control is used to the slave finger with grey GM(1,1) model, the prediction models are built by the signal of force acquired from sensors, the force controller enforces a relationship between the position of each finger and the force on the manipulated objects, and the weights of the current and the future force errors are automatic adjusted in integrated error according to the model precision. The force controllers can employ the information of past, present and future force to calculate an appropriate control correction to pre-compensate the force errors, thus it can obtain lower overshoot and faster response. Simulation results are presented to demonstrate the efficacy of the proposed master-slave force controllers.

A Comparative Review of Hand-Eye Calibration Techniques for Vision Guided Robots

Abstract: Hand-eye calibration enables proper perception of the environment in which a vision guided robot operates. Additionally, it enables the mapping of the scene in the robots frame. Proper hand-eye calibration is crucial when sub-millimetre perceptual accuracy is needed. For example, in robot assisted surgery, a poorly calibrated robot would cause damage to surrounding vital tissues and organs, endangering the life of a patient. A lot of research has gone into ways of accurately calibrating the hand-eye system of a robot with different levels of success, challenges, resource requirements and complexities. As such, academics and industrial practitioners are faced with the challenge of choosing which algorithm meets the implementation requirements based on the identified constraints. This review aims to give a general overview of the strengths and weaknesses of different hand-eye calibration algorithms available to academics and industrial practitioners to make an informed design decision, as well as incite possible areas of research based on the identified challenges. We also discuss different calibration targets, which is an important part of the calibration process that is often overlooked in the design process.

Robot unstacking method based on binocular stereoscopic vision

Abstract: The invention discloses a robot unstacking method based on binocular stereoscopic vision. The robot unstacking method includes the following steps of: simultaneously obtaining images within views of left and right eyes by using a binocular camera fixed right above a working area, and positioning a target by using a shape template matching method to obtain a three-dimensional coordinate under the camera coordinate system; converting from the camera coordinate system into a robot base coordinate system; arranging depth information and unstacking in a layered manner according to the detected target coordinate. According to the robot unstacking method based on binocular stereoscopic vision, target identification and three-dimensional positioning of product in an unstacking area are achieved directly through collecting binocular images, and thereby automatic unstacking task of the product is achieved, and the problems that manual unstacking is large in labor intensity and low in efficiency can be effectively overcome.

A Workpiece Localization Method for Robotic De-Palletizing Based on Region Growing and PPHT

Abstract: Aiming at the problem that the robot de-palletizing task is difficult to accomplish under unstable ambient light, a two-step method is proposed to realize the localization of workpieces, which in this work are woven bags. To begin with, Region Growing method is used to extract the whole target region in the original image, and the relationship model between image intensity and the optimal Region Growing threshold is established. Then, Progressive Probabilistic Hough Transform(PPHT) is used to locate each woven bag. To improve the system performance, the optimal parameters of the PPHT function in different illumination intervals are determined. Finally, experiments are conducted to verify the effectiveness of the proposed method. Experiment results demonstrate this method is robust and feasible.

Design and grip force control of dual-motor drive electric gripper with parallel fingers

Abstract: This paper designs a novel electric gripper with parallel fingers and each finger has a set of an independent drive motor and integrates a force sensor. The gripper with the flexibility of mechanical structure and control is mounted in the end of an industrial robot, and a flexible grip test platform is constructed based on an embedded controller. Prarllel position-force control algorithm is proposed to be used for the gripper, and dual fingers can be individually position-controlled or force-controlled. The grip force, position and speed can be set individually so that the clamping centre and strokes can be programmed to control with improved dexterity. It can make the resulting grip force rapidly track desired force with low overshoots to a tolerable limit and be quickly stabilized within an acceptable range. Robots grip experiments show that the gripper can provide flexible grip, improve the flexibility and reduce damages to the fragile and deformable objects during dynamic grip process.

A Comparison of High-Level Design Tools for SoC-FPGA on Disparity Map Calculation Example

Abstract: Modern SoC-FPGA that consists of FPGA with embedded ARM cores is being popularized as an embedded vision system platform. However, the design approach of SoC-FPGA applications still follows traditional hardware-software separate workflow, which becomes the barrier of rapid product design and iteration on SoC-FPGA. High-Level Synthesis (HLS) and OpenCL-based system-level design approaches provide programmers the possibility to design SoC-FGPA at system-level with an unified development environment for both hardware and software. To evaluate the feasibility of high-level design approach especially for embedded vision applications, Vivado HLS and Altera SDK for OpenCL, representative and most popular commercial tools in market, are selected as evaluation design tools, disparity map calculation as targeting application. In this paper, hardware accelerators of disparity map calculation are designed with both tools and implemented on Zedboard and SoCKit development board, respectively. Comparisons between design tools are made in aspects of supporting directives, accelerator design process, and generated hardware performance. The results show that both tools can generate efficient hardware for disparity map calculation application with much less developing time. Moreover, we can also state that, more directives (e.g., interface type, array reshape, resource type specification) are supported, but more hardware knowledge is required, in Vivado HLS. In contrast, Altera SDK for OpenCL is relatively easier for software programmers who is new to hardware, but with the price of more resources usage on FPGA for similar hardware accelerator generation.